feat(读文章写摘要):支持pdf文件批量阅读及总结 #101

crazy_functions/批量总结PDF文档.py

@@ -0,0 +1,74 @@
+from predict import predict_no_ui
+from toolbox import CatchException, report_execption, write_results_to_file, predict_no_ui_but_counting_down
+fast_debug = False
+
+
+def 解析PDF(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt):
+    import time, glob, os, codecs, fitz
+    print('begin analysis on:', file_manifest)
+    for index, fp in enumerate(file_manifest):
+        with fitz.open(fp) as doc:
+            file_content = ""
+            for page in doc:
+                file_content += page.getText()
+            print(file_content)
+
+        prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index==0 else ""
+        i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
+        i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
+        chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
+        print('[1] yield chatbot, history')
+        yield chatbot, history, '正常'
+
+        if not fast_debug: 
+            msg = '正常'
+            # ** gpt request **
+            gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temperature, history=[])   # 带超时倒计时
+
+            print('[2] end gpt req')
+            chatbot[-1] = (i_say_show_user, gpt_say)
+            history.append(i_say_show_user); history.append(gpt_say)
+            print('[3] yield chatbot, history')
+            yield chatbot, history, msg
+            print('[4] next')
+            if not fast_debug: time.sleep(2)
+
+    all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)])
+    i_say = f'根据以上你自己的分析，对全文进行概括，用学术性语言写一段中文摘要，然后再写一段英文摘要（包括{all_file}）。'
+    chatbot.append((i_say, "[Local Message] waiting gpt response."))
+    yield chatbot, history, '正常'
+
+    if not fast_debug: 
+        msg = '正常'
+        # ** gpt request **
+        gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say, chatbot, top_p, temperature, history=history)   # 带超时倒计时
+
+        chatbot[-1] = (i_say, gpt_say)
+        history.append(i_say); history.append(gpt_say)
+        yield chatbot, history, msg
+        res = write_results_to_file(history)
+        chatbot.append(("完成了吗？", res))
+        yield chatbot, history, msg
+
+
+def 批量总结PDF文档(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT):
+    history = []    # 清空历史，以免输入溢出
+    import glob, os
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        yield chatbot, history, '正常'
+        return
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] + \
+                    [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)] # + \
+                    # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
+                    # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
+    if len(file_manifest) == 0:
+        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.pdf文件: {txt}")
+        yield chatbot, history, '正常'
+        return
+    
+    yield from 解析PDF(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)
+    

crazy_functions/读文章写摘要.py

@@ -48,54 +48,8 @@ def 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, hist
         yield chatbot, history, msg
 
 
-def 解析PDF(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt):
-    import time, glob, os, codecs, fitz
-    print('begin analysis on:', file_manifest)
-    for index, fp in enumerate(file_manifest):
-        with fitz.open(fp) as doc:
-            file_content = ""
-            for page in doc:
-                file_content += page.getText()
-            print(file_content)
-
-        prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index==0 else ""
-        i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
-        i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
-        chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
-        print('[1] yield chatbot, history')
-        yield chatbot, history, '正常'
-
-        if not fast_debug: 
-            msg = '正常'
-            # ** gpt request **
-            gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temperature, history=[])   # 带超时倒计时
-
-            print('[2] end gpt req')
-            chatbot[-1] = (i_say_show_user, gpt_say)
-            history.append(i_say_show_user); history.append(gpt_say)
-            print('[3] yield chatbot, history')
-            yield chatbot, history, msg
-            print('[4] next')
-            if not fast_debug: time.sleep(2)
-
-    all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)])
-    i_say = f'根据以上你自己的分析，对全文进行概括，用学术性语言写一段中文摘要，然后再写一段英文摘要（包括{all_file}）。'
-    chatbot.append((i_say, "[Local Message] waiting gpt response."))
-    yield chatbot, history, '正常'
-
-    if not fast_debug: 
-        msg = '正常'
-        # ** gpt request **
-        gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say, chatbot, top_p, temperature, history=history)   # 带超时倒计时
-
-        chatbot[-1] = (i_say, gpt_say)
-        history.append(i_say); history.append(gpt_say)
-        yield chatbot, history, msg
-        res = write_results_to_file(history)
-        chatbot.append(("完成了吗？", res))
-        yield chatbot, history, msg
-
 
+@CatchException
 def 读文章写摘要(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT):
     history = []    # 清空历史，以免输入溢出
     import glob, os
@@ -106,15 +60,11 @@ def 读文章写摘要(txt, top_p, temperature, chatbot, history, systemPromptTx
         report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield chatbot, history, '正常'
         return
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] + \
-                    [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)] # + \
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] # + \
                     # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
                     # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex或.pdf文件: {txt}")
+        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
         yield chatbot, history, '正常'
         return
-    if '.pdf' in file_manifest[0]:
-        yield from 解析PDF(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)
-    else:
-        yield from 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)
+    yield from 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)

functional_crazy.py

@@ -1,6 +1,7 @@
 
 def get_crazy_functionals():
     from crazy_functions.读文章写摘要 import 读文章写摘要
+    from crazy_functions.批量总结PDF文档 import 批量总结PDF文档
     from crazy_functions.生成函数注释 import 批量生成函数注释
     from crazy_functions.解析项目源代码 import 解析项目本身
     from crazy_functions.解析项目源代码 import 解析一个Python项目
@@ -28,6 +29,10 @@ def get_crazy_functionals():
             "Color": "stop",    # 按钮颜色
             "Function": 读文章写摘要
         },
+        "[实验] 批量总结pdf文档并生成双语摘要（配合input输入框）": {
+            "Color": "stop",    # 按钮颜色
+            "Function": 批量总结PDF文档
+        },
         "[实验] 批量生成函数注释（配合input输入框）": {
             "Color": "stop",    # 按钮颜色
             "Function": 批量生成函数注释